Bad results by the pre-trained model when tested on an unseen image

[onchiptech]

Hello,

I run the "Try-On" task inference with the pre-trained model on the following image which is not in the dataset.

As you can see the below output generated is not good. Face and hands are not rendered properly.

But for the images in the datasets, I am getting good results.

Any suggestions?

Regards, Surendra

[cuiaiyu]

The pretrained model has the face overfitting issue for outlier data. For try-on task, I'd suggest something like directly copying and pasting the face as

final_img = face_mask * input_img + (1-face_mask) * generated_image.

where the face_mask you can get from the human parsing which is part of the inputs.

[vinodbukya6]

Hi @onchiptech

Did you solve the face overfitting issue?

When I used this method, Results are not good.

final_img = face_mask * input_img + (1-face_mask) * generated_image.